OLMo-7B: benchmark results
Provider: Allen AI. Access: Open.
Unified ELO 1174 ± 23, rank #1552 of 1605 rated models, from 93 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Lite - LegalBench - International Citizenship Questions | 54 | Exact Match (%) | 47.8 |
| Open Portuguese LLM - FaQuAD NLI | 43.97 | Macro F1 (%) | 17.1 |
| Open Portuguese LLM - OAB Exams | 25.24 | Accuracy (%) | 15.9 |
| HELM NarrativeQA | 59.71 | F1 (%) | 13.3 |
| HELM Lite - LegalBench - Corporate Lobbying | 19.59 | Exact Match (%) | 12.2 |
| HELM Lite - WMT 2014 (ru-en) | 12.42 | BLEU-4 (%) | 12.2 |
| HELM NaturalQuestions (Open) | 60.35 | F1 (%) | 12.2 |
| Open Portuguese LLM - BLUEX | 21 | Accuracy (%) | 11.2 |
| HELM NaturalQuestions (Closed) | 25.86 | F1 (%) | 11.1 |
| Open Portuguese LLM - ENEM | 19.73 | Accuracy (%) | 11.1 |
| Open Portuguese LLM - ASSIN2 RTE | 33.97 | Macro F1 (%) | 8.5 |
| HELM MMLU - High School Statistics | 45.37 | EM | 7.1 |
Interactive version: theaggregate.ai/model?slug=olmo-7b · How It Works · Data refreshed daily, snapshot 2026-09-26.